import pandas as pd

# # Define the path to your Excel file
# excel_file_path = r'..\Documents\All_Data_2023.xlsx'

# # Define the name of the sheet you want to load
# sheet_name_to_load = 'Final data'

# # Define the path for the output CSV file
# csv_output_path = r'..\data\final_data_2023.csv'

# try:
#     # Read the specified sheet from the Excel file into a pandas DataFrame
#     df = pd.read_excel(excel_file_path, sheet_name=sheet_name_to_load)

#     # Save the DataFrame to a CSV file
#     # index=False prevents pandas from writing the DataFrame index as a column
#     df.to_csv(csv_output_path, index=False)

#     print(f"Sheet '{sheet_name_to_load}' from '{excel_file_path}' successfully saved to '{csv_output_path}'")

# except FileNotFoundError:
#     print(f"Error: The file '{excel_file_path}' was not found.")
# except Exception as e:
#     # Catches other potential errors like the sheet name not existing
#     print(f"An error occurred: {e}")

csv_output_path = r'..\data\final_data_2023.csv'
df = pd.read_csv(csv_output_path)

df.head()

# Import the ProfileReport class
from ydata_profiling import ProfileReport

# Generate the profile report
# title is optional but helpful for identifying the report
profile = ProfileReport(df, title="Iris Data Profiling Report")

# Display the report within the notebook
# This works well in Jupyter environments
profile.to_notebook_iframe()

Summarize dataset:   0%|          | 0/5 [00:00<?, ?it/s]

100%|██████████| 27/27 [00:00<00:00, 774.74it/s]

Generate report structure:   0%|          | 0/1 [00:00<?, ?it/s]

Render HTML:   0%|          | 0/1 [00:00<?, ?it/s]

	Entry	Entry_species	Species	Population	Date	ID	Flower_No.	Length_mm	Width_mm	Ratio_len/wid	...	Flowers_total	Marked	Wilted	Fruits_marked	Fruits_notmarked	Fruits_total	Fruit	seeds	weight	Avg.weight
0	1	23	I.atropurpurea	NET	2023-02-26	3	1	63.4	55.0	1.152727	...	3.0	1.0	2.0	0.0	0.0	0.0	0.0	0.0	0.0	0.000000
1	2	24	I.atropurpurea	NET	2023-02-26	10	1	96.0	78.5	1.222930	...	3.0	2.0	1.0	1.0	0.0	1.0	1.0	14.0	1008.5	72.035714
2	3	36	I.atropurpurea	NET	2023-03-05	10	2	77.1	63.4	1.216088	...	NaN	NaN	NaN	NaN	NaN	NaN	0.0	0.0	0.0	0.000000
3	4	46	I.atropurpurea	NET	2023-03-05	29	1	61.0	57.2	1.066434	...	2.0	1.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.000000
4	5	35	I.atropurpurea	NET	2023-02-26	34	1	62.5	59.7	1.046901	...	2.0	1.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.000000